Qwen3 30B A3B Instruct 2507
Qwen · Open weights · Released Jul 29, 2025 · qwen/qwen3-30b-a3b-instruct-2507
Best $0.09 in / $0.30 out via DekaLLM
262K contextToolsStructured outputPrompt cachingOpen weights
Available from 3 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 9 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| DEDekaLLM | $0.09 | $0.30 | — | 262K | — | 2.5s | 47 tok/s | 99.5% |
| $0.09 | $0.30 | — | 262K | fp8 | 1.9s | 56 tok/s | 98.8% | |
| $0.10 | $0.30 | $0.10 | 262K | fp8 | 0.82s | 162 tok/s | 98.8% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 9 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Oct 10, 2026endpoint removed · alibaba5 → 3
Oct 10, 2026endpoint removed · streamlake5 → 3
Oct 5, 2026endpoint removed · primeintellect6 → 5
Oct 4, 2026endpoint added · primeintellect5 → 6
About
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Specifications
Context window262,144
Max output235,929
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 29, 2025
Knowledge cutoff2025-06-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-30b-a3b-instruct-2507)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks9 minutes ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.